- Number
- 20260321061
- Published
- 2026-10-15
- Filed
- 2026-06-25
- Assignee
- DISNEY ENTERPRISES, INC.
- Inventors
- HALE; Gregory Brooks, MARKOWITZ; Gary D., WILKINSON; Clifford Aron, CHEN; Ching-Chien
- CPC
- G06V40/20; G06V20/41; G06V40/10; G06V40/1365; G09B19/003
- Verdict
- Low Notable software
- First reported
- 2026-W42 (2026-10-16)
- Source
- Google Patents · FreePatentsOnline
The keeper's note
A vision system that watches video to spot a person and a specific event happening to them, then scores how confident it is before acting on the detection.
Abstract
Methods, systems, and non-transitory computer-readable media are described for providing assistance based on video analysis. One or more processors are configured to receive and analyze video data using a machine learning model to detect an individual in a first portion of the video data and detect an event involving the individual in a subsequent portion, determine a measure of confidence indicative of a likelihood of accurately detecting the event, determine one or more confidence factors based on detecting a change, difference, or audio data, increase the measure of confidence using the confidence factors to determine a modified measure of confidence, which is compared to a confidence threshold, and generate a notification to cause assistance to be provided to the individual when the modified measure of confidence satisfies the confidence threshold.
Background
BACKGROUND
Closed-circuit television (CCTV) is a system that includes video camera devices that provide signals (e.g., video feeds) to specified monitors located at a specified location. In this regard, a CCTV system differs from a broadcast television system that broadcasts signals to multiple monitors located at multiple locations. A CCTV system is typically used to perform surveillance of areas monitored by the video camera devices. SUMMARY
In some implementations, a method performed by a guest assistance platform includes analyzing video data of an environment that includes a liquid substance, wherein the video data is analyzed using a machine learning model trained to detect objects in the liquid substance; detecting an individual in the liquid substance based on analyzing the video data; determining a measure of confidence associated with detecting the individual in the liquid substance; determining one or more confidence factors associated with detecting the individual in the liquid substance; modifying the measure of confidence, using the one or more confidence factors, to obtain a modified measure of confidence; determining whether the modified measure of confidence satisfies a confidence threshold; and selectively causing assistance to be provided to the individual or continue analyzing the video data based on whether the modified measure of confidence satisfies the confidence threshold, wherein the assistance is provided based on the modified measure
Claims
1. A method comprising: receiving, by one or more processors, video data of an environment; detecting, by the one or more processors using a machine learning model, a first individual in a first portion of the video data; detecting, by the one or more processors using the machine learning model, an event involving the first individual in a second portion of the video data following the first portion; determining, by the one or more processors, a measure of confidence indicative of a likelihood of the machine learning model accurately detecting the event; determining, by the one or more processors, one or more confidence factors based on detecting at least one of: (i) a change, between the first portion of the video data and the second portion of the video data, in a position of an item belonging to the first individual relative to the first individual; (ii) a difference, between the first portion of the video data and the second portion of the video data, in a number of individuals within a region of the environment; or (iii) audio data associated with the event; increasing, by the one or more processors, the measure of confidence using the one or more confidence factors to determine a modified measure of confidence; comparing, by the one or more processors, the modified measure of confidence to a confidence threshold; and generating, by the one or more processors, a notification to a client device to cause assistance to be provided to the first individual in response to determining that the modified measure of confidence satisfies the confidence threshold. ||
8. A system comprising one or more processors configured to: receive video data of an environment; detect, using a machine learning model, a first individual in a first portion of the video data; detect, using the machine learning model, an event involving the first individual in a second portion of the video data following the first portion; determine a measure of confidence indicative of a likelihood of the machine learning model accurately detecting the event; determine one or more confidence factors based on detecting at least one of: (i) a change, between the first portion of the video data and the second portion of the video data, in a position of an item belonging to the first individual relative to the first individual; (ii) a difference, between the first portion of the video data and the second portion of the video data, in a number of individuals within a region of the environment; or (iii) audio data associated with the event; increase the measure of confidence using the one or more confidence factors to determine a modified measure of confidence; compare the modified measure of confidence to a confidence threshold; and generate a notification to a client device to cause assistance to be provided to the first individual in response to determining that the modified measure of confidence satisfies the confidence threshold. ||
15. A non-transitory computer-readable medium comprising: one or more instructions that, when executed by one or more processors, cause the one or more processors to: receive video data of an environment; detect, using a machine learning model, a first individual in a first portion of the video data; detect, using the machine learning model, an event involving the first individual in a second portion of the video data following the first portion; determine a measure of confidence indicative of a likelihood of the machine learning model accurately detecting the event; determine one or more confidence factors based on detecting at least one of: (i) a change, between the first portion of the video data and the second portion of the video data, in a position of an item belonging to the first individual relative to the first individual; (ii) a difference, between the first portion of the video data and the second portion of the video data, in a number of individuals within a region of the environment; or (iii) audio data associated with the event; increase the measure of confidence using the one or more confidence factors to determine a modified measure of confidence; compare the modified measure of confidence to a confidence threshold; and generate a notification to a client device to cause assistance to be provided to the first individual in response to determining that the modified measure of confidence satisfies the confidence threshold.